Fuzzy Integral-Based Multi-Classifiers Ensemble for Android Malware Classification
One of the most commonly used operating systems for smartphones is Android. The open-source nature of the Android operating system and the ability to include third-party Android apps from various markets has led to potential threats to user privacy. Malware developers use sophisticated methods that...
Guardado en:
Autores principales: | , , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
MDPI AG
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/fb015018fa704d64a0029fe464c51788 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:fb015018fa704d64a0029fe464c51788 |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:fb015018fa704d64a0029fe464c517882021-11-25T18:16:50ZFuzzy Integral-Based Multi-Classifiers Ensemble for Android Malware Classification10.3390/math92228802227-7390https://doaj.org/article/fb015018fa704d64a0029fe464c517882021-11-01T00:00:00Zhttps://www.mdpi.com/2227-7390/9/22/2880https://doaj.org/toc/2227-7390One of the most commonly used operating systems for smartphones is Android. The open-source nature of the Android operating system and the ability to include third-party Android apps from various markets has led to potential threats to user privacy. Malware developers use sophisticated methods that are intentionally designed to bypass the security checks currently used in smartphones. This makes effective detection of Android malware apps a difficult problem and important issue. This paper proposes a novel fuzzy integral-based multi-classifier ensemble to improve the accuracy of Android malware classification. The proposed approach utilizes the Choquet fuzzy integral as an aggregation function for the purpose of combining and integrating the classification results of several classifiers such as XGBoost, Random Forest, Decision Tree, AdaBoost, and LightGBM. Moreover, the proposed approach utilizes an adaptive fuzzy measure to consider the dynamic nature of the data in each classifier and the consistency and coalescence between each possible subset of classifiers. This enables the proposed approach to aggregate the classification results from the multiple classifiers. The experimental results using the dataset, consisting of 9476 Android goodware apps and 5560 malware Android apps, show that the proposed approach for Android malware classification based on the Choquet fuzzy integral technique outperforms the single classifiers and achieves the highest accuracy of 95.08%.Altyeb TahaOmar BarukabSharaf MalebaryMDPI AGarticleAndroid malware classificationensemble learningchoquet fuzzy integralMathematicsQA1-939ENMathematics, Vol 9, Iss 2880, p 2880 (2021) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
Android malware classification ensemble learning choquet fuzzy integral Mathematics QA1-939 |
spellingShingle |
Android malware classification ensemble learning choquet fuzzy integral Mathematics QA1-939 Altyeb Taha Omar Barukab Sharaf Malebary Fuzzy Integral-Based Multi-Classifiers Ensemble for Android Malware Classification |
description |
One of the most commonly used operating systems for smartphones is Android. The open-source nature of the Android operating system and the ability to include third-party Android apps from various markets has led to potential threats to user privacy. Malware developers use sophisticated methods that are intentionally designed to bypass the security checks currently used in smartphones. This makes effective detection of Android malware apps a difficult problem and important issue. This paper proposes a novel fuzzy integral-based multi-classifier ensemble to improve the accuracy of Android malware classification. The proposed approach utilizes the Choquet fuzzy integral as an aggregation function for the purpose of combining and integrating the classification results of several classifiers such as XGBoost, Random Forest, Decision Tree, AdaBoost, and LightGBM. Moreover, the proposed approach utilizes an adaptive fuzzy measure to consider the dynamic nature of the data in each classifier and the consistency and coalescence between each possible subset of classifiers. This enables the proposed approach to aggregate the classification results from the multiple classifiers. The experimental results using the dataset, consisting of 9476 Android goodware apps and 5560 malware Android apps, show that the proposed approach for Android malware classification based on the Choquet fuzzy integral technique outperforms the single classifiers and achieves the highest accuracy of 95.08%. |
format |
article |
author |
Altyeb Taha Omar Barukab Sharaf Malebary |
author_facet |
Altyeb Taha Omar Barukab Sharaf Malebary |
author_sort |
Altyeb Taha |
title |
Fuzzy Integral-Based Multi-Classifiers Ensemble for Android Malware Classification |
title_short |
Fuzzy Integral-Based Multi-Classifiers Ensemble for Android Malware Classification |
title_full |
Fuzzy Integral-Based Multi-Classifiers Ensemble for Android Malware Classification |
title_fullStr |
Fuzzy Integral-Based Multi-Classifiers Ensemble for Android Malware Classification |
title_full_unstemmed |
Fuzzy Integral-Based Multi-Classifiers Ensemble for Android Malware Classification |
title_sort |
fuzzy integral-based multi-classifiers ensemble for android malware classification |
publisher |
MDPI AG |
publishDate |
2021 |
url |
https://doaj.org/article/fb015018fa704d64a0029fe464c51788 |
work_keys_str_mv |
AT altyebtaha fuzzyintegralbasedmulticlassifiersensembleforandroidmalwareclassification AT omarbarukab fuzzyintegralbasedmulticlassifiersensembleforandroidmalwareclassification AT sharafmalebary fuzzyintegralbasedmulticlassifiersensembleforandroidmalwareclassification |
_version_ |
1718411417115164672 |